Jason Joseph Corso

Prepared on October 11, 2020

Contact University of Michigan Voxel51 1301 Beal Avenue 410 N 4th Ave 4238 EECS 3rd Floor Ann Arbor, MI 48109-2122 Ann Arbor, MI 48104-1104 Phone: 734-647-8833 Phone: 734-531-9349 Email: [email protected] Email: [email protected] Web: http://web.eecs.umich.edu/∼jjcorso Web: https://voxel51.com

Background Date of Birth: 6 August 1978 Place of Birth: New York, USA Citizenship: USA Security Clearance: On Request

Appointments Director of the Stevens Institute for Artificial Intelligence Hoboken, NJ Viola Ward Brinning and Elbert Calhoun Brinning Professor of Computer Science Stevens Institute of Technology 1/2021 - Ongoing Professor Ann Arbor, MI Electrical Engineering and Computer Science University of Michigan 8/2019 - 12/2020 Co-Founder and CEO Ann Arbor, MI Voxel51, Inc. 12/2016 - Present Full list of appointments begins on page 26

Research Focus Cognitive systems and their entanglement with vision, language, physical constraints, robotics, autonomy, and the semantics of the natural world, both in corner-cases and at scale.

Research Areas Computer Vision Robot Perception Human Language Data Science / Machine Learning Artificial Intelligence Software Systems

Education University of California, Los Angeles Los Angeles, CA Post-Doc in Neuroscience and Statistics 2006-2007 Advisors: Dr. Alan Yuille and Dr. Arthur Toga

The Baltimore, MD Ph.D. in Computer Science 6/2006 Advisor: Dr. Gregory D. Hager Dissertation Title:“Techniques for Vision-Based Human-Computer Interaction” Full list of education begins on page 26

Distinctions EECS Outstanding Achievement Award 2018 University of Michigan, Department of Electrical Engineering and Computer Science Best Associate Editor Award for ICRA 2016 Google Faculty Research Award 2015 Computational PB&J: Learning from Instructional Video Best Paper Award at ECDM 2012 for Efficient Max-Margin Metric Learning 2012 SUNY at Buffalo Young Investigator Award 2011 Army Research Office Young Investigator Award 2010 Guidance By Semantics–High-Level Visual Inference to Improve Vision-based Mobile Robot Localization National Science Foundation CAREER Award 2009 Generalized Image Understanding with Probabilistic Ontologies and Dynamic Adaptive Graph Hierarchies DARPA Computer Science Study Group 2009 A distinction awarded to junior faculty for revolutionary activities in defense-relevant research

1 of 27 SUNY at Buffalo STOR Visionary Innovator 2009 Awarded for licensing technology to industry. Best New Development 2006 UCLA Laboratory of Neuroimaging, CCB AHM Segmentation Contest Link Foundation Fellowship in Advanced Simulation and Training 2003 James D Rozics Computer Science Medal - Loyola College in Maryland 2000 Awarded to the computer science student ranked first upon graduation Upsilon Pi Epsilon Scholarship, Computer Science Honors Society 1998 Hauber Summer Science Research Fellowship - Loyola College in Maryland 1998

Publications Journal Articles Qualifiers from date of publication added where known: Impact Factor (IF), h5-Index (h5) provided by Google Scholar.

J28. R. Szeto, X. Sun, K. Lu, and J. J. Corso. A Temporally-Aware Interpolation Network for Video Frame Inpainting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020 (to appear). IF: 17.730; h5: 127 (IEEE TPAMI) J27. Y. Yan, C. Xu, D. Cai, and J. J. Corso. A weakly supervised multi-task ranking framework for actor-action semantic segmentation. International Journal of Computer Vision, 2019 (to appear). IF: 11.541; h5: 66 (IJCV) J26. S. Kumar, V. Dhiman, P. Koch, and J. J. Corso. Learning compositional sparse bimodal models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(5):1032–1044, 2018. IF: 8.329; h5: 114 (IEEE TPAMI) J25. D. Sarikaya, J. J. Corso, and K. A. Guru. Detection and localization of robotic tools in robot- assisted surgery videos using deep neural networks for region proposal and detection. IEEE Transactions on Medical Imaging, 36(7):1542–1549, 2017. IF: 3.76; h5: 59 (IEEE TMI) J24. T. Han, H. Yao, C. Xu, X. Sun, Y. Zhang, and J. J. Corso. Dancelets mining for video recom- mendation based on dance styles. IEEE Transactions on Multimedia, 19(4), 2017. IF: 2.536; h5: 51 (IEEE TMM) J23. C. Chen and J. J. Corso. Joint occlusion boundary detection and figure/ground assignment by extracting common-fate fragments in a back-projection scheme. Pattern Recognition, 64:15– 28, 2017. IF: 3.399; h5: 67 (PR) J22. C. Xiong, D. M. Johnson, and J. J. Corso. Active clustering with model-based uncertainty reduction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(1):5–17, 2017. Original Version: ArXiv 1402.1783. IF: 5.694; h5: 108 (IEEE TPAMI) J21. C. Xu and J. J. Corso. LIBSVX: A supervoxel library and benchmark for early video process- ing. International Journal of Computer Vision, 119:272–290, 2016. IF: 4.270; h5: 65 (IJCV) J20. D. M. Johnson, C. Xiong, and J. J. Corso. Semi-supervised nonlinear distance metric learn- ing via forests of max-margin cluster hierarchies. IEEE Transactions on Knowledge and Data Engineering, 28(4):1035–1046, 2016. IF: 2.067; h5: 65 (IEEE TKDE) J19. B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, J. Kirby, Y. Burren, N. Porz, J. Slotboom, R. Wiest, L. Lanczi, R. Gerstner, M.-A. Weber, T. Arbel, B. B. Avants, N. Ayache, P. Buendia, D. L. Collins, N. Cordier, J. J. Corso, A. Criminisi, T. Das, H. Delingette, C. Demi- ralp, C. R. Durst, M. Dojat, S. Doyle, J. Festa, F. Forbes, E. Geremia, B. Glocker, P. Golland, X. Guo, A. Hamamci, K. M. Iftekharuddin, R. Jena, N. M. John, E. Konukoglu, D. Lashkari, J. A. Mariz, R. Meier, S. Pereira, D. Precup, S. J. Price, T. Riklin Raviv, S. Reza, M. Ryan, D. Sarikaya, L. Schwartz, H.-C. Shin, J. Shotton, C. A. Silva, N. Sousa, N. K. Subbanna, G. Szekely, T. J. Taylor, O. M. Thomas, N. J. Tustison, G. Unal, F. Vasseur, M. Wintermark, D. H. Ye, L. Zhao, B. Zhao, D. Zikic, M. Prastawa, M. Reyes, and K. Van Leemput. The mul- timodal brain tumor image segmentation benchmark (brats). IEEE Transactions on Medical Imaging, 34(10):1993–2024, 2015. IF: 3.39; h5: 63 (IEEE TMI) J18. S. Kumar, N. Ahmidi, G. Hager, P. Singhal, J. J. Corso, and V. Krovi. Surgical performance assessment. ASME Dynamics Systems and Control Magazine, 3(3):7–10, 2015. (ASME) J17. C. Xu, R. F. Doell, S. J. Hanson, C. Hanson, and J. J Corso. A study of actor and action seman- tic retention in video supervoxel segmentation. International Journal of Semantic Computing,

2 of 27 2014. Selected as a Best Paper from ICSC; an earlier version appeared as arXiv:1311.3318. h5: 13 (IJSC) J16. P. Agarwal, S. Kumar, J. Ryde, J. J. Corso, and V. N. Krovi. Estimating dynamics on-the-fly using monocular video for vision-based robotics. IEEE/ASME Transactions on Mechatronics, 19(4):1412–1423, 2014. IF: 3.135; h5: 37 (IEEE/ASME TMECH) J15. W. Wu, A. Y. C. Chen, L. Zhao, and J. J. Corso. Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features. International Journal of Computer Aided Radiology and Surgery, 9(2):241–253, 2014. IF: 1.364; h5: 17 (IJCARS) J14. S. Oh, S. McCloskey, I. Kim, A. Vahdat, K. Cannons, H. Hajimirsadeghi, G. Mori, A. G. A. Perera, M. Pandey, and J. J. Corso. Multimedia event detection with multimodal feature fusion and temporal concept localization. Machine Vision and Applications, 25:49–69, 2014. IF: 1.009; h5: 21 (MVA) J13. J. A. Delmerico, P. David, and J. J. Corso. Building facade detection, segmentation, and parameter estimation for mobile robot stereo vision. Image and Vision Computing, 31(11):841– 852, 2013. IF: 1.952; h5: 42 (IVC) J12. Y. Miao and J. J. Corso. Hamiltonian streamline guided feature extraction with application to face detection. Journal of Neurocomputing, 120:226–234, 2013. Early version appears as arXiv.org tech report 1108.3525v1. IF: 1.58; h5: 44 (NEUCOM) J11. J. J. Corso. Toward parts-based scene understanding with pixel-support parts-sparse pic- torial structures. Pattern Recognition Letters: Special Issue on Scene Understanding and Behavior Analysis, 34(7):762–769, 2013. Early version appears as arXiv.org tech report 1108.4079v1. IF: 1.034; h5: 43 (PRL) J10. R. S. Alomari, J. J. Corso, V. Chaudhary, and G. Dhillon. Toward a clinical lumbar CAD: Herniation diagnosis. International Journal of Computer Aided Radiology and Surgery, 6(1):119– 126, 2011. IF: 1.364; h5: 17 (IJCARS) J9. R. S. Alomari, J. J. Corso, and V. Chaudhary. Labeling of lumbar discs using both pixel- and object-level features with a two-level probabilistic model. IEEE Transactions on Medical Imaging, 30(1):1–10, 2011. IF: 4.027; h5: 48 (IEEE TMI) J8. P. B. Noel,¨ A. Walczak, J. Xu, J. J. Corso, K. R. Hoffmann, and S. Schafer. GPU-based cone beam computed tomography. Computer Methods and Programs in Biomedicine, 98(3):271–277, 2010. IF: 1.589; h5: 29 (CMPB) J7. R. S. Alomari, J. J. Corso, V. Chaudhary, and G. Dhillon. Computer-aided diagnosis of lumbar disc pathology from clinical lower spine MRI. International Journal of Computer Aided Radiology and Surgery, 5(3):287–293, 2010. IF: 1.364; h5: 17 (IJCARS) J6. J. J. Corso and G. D. Hager. Image Description with Features that Summarize. Computer Vision and Image Understanding, 113:446–458, 2009. IF: 2.202; h5: 39 (CVIU) J5. J. J. Corso, G. Ye, D. Burschka, and G. D. Hager. A Practical Paradigm and Platform for Video-Based Human-Computer Interaction. IEEE Computer, 42(5):48–55, 2008. IF: 2.111; h5: 49 (IEEE Computer) J4. J. J. Corso, E. Sharon, S. Dube, S. El-Saden, U. Sinha, and A. Yuille. Efficient Multilevel Brain Tumor Segmentation with Integrated Bayesian Model Classification. IEEE Transactions on Medical Imaging, 27(5):629–640, 2008. IF: 4.027; h5: 48 (IEEE TMI) J3. J. J. Corso, G. Ye, and G. D. Hager. Analysis of Composite Gestures with a Coherent Proba- bilistic Graphical Model. Virtual Reality, 8(4):242–252, 2005. IF: 0.341; h5: 13 (VR) J2. D. Burschka, J. J. Corso, M. Dewan, W. Lau, M. Li, H. Lin, P. Marayong, N. Ramey, G. D. Hager, B. Hoffman, D. Larkin, and C. Hasser. Navigating Inner Space: 3-D Assistance for Minimally Invasive Surgery. Robotics and Autonomous System, 2005. IF: 1.615; h5: 37 (RAS) J1. G. Ye, J. J. Corso, D. Burschka, and G. D. Hager. VICs: A Modular HCI Framework Using Spatio-Temporal Dynamics. Machine Vision and Applications, 16(1):13–20, 2004. IF: 1.009; h5: 21 (MVA)

3 of 27 Conference Proceedings (Peer-Reviewed) Qualifiers added where known: Acceptance Rate∗ (AR) with ∗ indicating historical, not year-specific rate, h5-Index (h5) provided by Google Scholar (at time of publication).

2020 C114. L. Zhou, H. Palangi, L. Zhang, H. Hu, J. J. Corso, and J. Gao. Unified vision-language pre-training for image captioning and vqa. In Proceedings of AAAI Conference on Artificial Intelligence, 2020. AR: 20.6%; h5: 95 (AAAI) C113. B. Griffin and J. J. Corso. Learning object depth from camera motion and video object segmentation. In Proceedings of European Conference on Computer Vision, 2020. AR: 26%; h5: 144 (ECCV) C112. K. Min and J. J. Corso. Adversarial background-aware loss for weakly-supervised temporal activity localization. In Proceedings of European Conference on Computer Vision, 2020. AR: 26%; h5: 144 (ECCV) C111. M. El Banani, J. J. Corso, and D. Fouhey. Novel object viewpoint estimation through re- construction alignment. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2020. AR: 22%; h5: 299 (CVPR) C110. M. Ravi Ganesh and J. J. Corso. Rethinking curriculum learning with incremental labels and adaptive compensation. In Proceedings of the British Machine Vision Conference, 2020. AR: 29%; h5: 57 (BMVC) C109. V. Florence, J. J. Corso, and B. Griffin. Robot-supervised learning for object segmentation. In Proceedings of IEEE International Conference on Robotics and Automation, 2020. AR: 42%; h5: 82 (ICRA) C108. B. Griffin, V. Florence, and J. J. Corso. Video object segmentation-based visual servo control and object depth estimation on a mobile robot. In Proceedings of IEEE Winter Conference on Applications of Computer Vision, 2020. AR∗: 35%; h5: 46 (WACV) 2019 C107. K. Min and J. J. Corso. TASED-net: Temporally-aggregating spatial encoder-decoder net- work for video saliency detection. In Proceedings of IEEE International Conference on Computer Vision, 2019. AR: 25%; h5: 129 (ICCV) C106. B. Griffin and J. J. Corso. BubbleNets: Learning to select the guidance frame in video object segmentation by deep sorting frames. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2019. AR: 5.6% (Oral; Best Paper Finalist); h5: 188 (CVPR) C105. L. Zhou, Y. Kalantidis, X. Chen, J. J. Corso, and M. Rohrbach. Grounded video description. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2019. AR: 5.6% (Oral); h5: 188 (CVPR) C104. H. Tang, D. Xu, Y. Yan, Y. Wang, J. J. Corso, and N. Sebe. Multi-channel attention selection GAN with cascaded semantic guidance for cross-view image translation. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2019. AR: 5.6% (Oral); h5: 188 (CVPR) C103. H. Huang, L. Zhou, W. Zhang, J. J. Corso, and C. Xu. Dynamic graph modules for modeling object-object interactions in activity recognition. In Proceedings of the British Machine Vision Conference, 2019. AR: 28%; h5: 46 (BMVC) C102. H. Tang, X. Chen, W. Wang, D. Xu, J. J. Corso, N. Sebe, and Y. Yan. Attribute-guided sketch generation. In Proceedings of IEEE Conference on Automatic Face and Gesture Recognition, 2019. AR∗: 30%; h5: 36 (FG) C101. J. Y. Song, S. J. Lemmer, M. X. Liu, S. Yan, J. Kim, J. J. Corso, and W. S. Lasecki. Popup: Reconstructing 3d video using particle filtering to aggregate crowd responses. In Proceedings of ACM International Conference on Intelligent User Interfaces, 2019. AR: 25%; h5: 27 (IUI) C100. B. Griffin and J. J. Corso. Tukey-inspired video object segmentation. In Proceedings of IEEE Winter Conference on Applications of Computer Vision, 2019. AR: 37%; h5: 38 (WACV) 2018 C99. L. Zhou, C. Xu, and J. J. Corso. Towards automatic learning of procedures from web instruc- tional videos. In Proceedings of AAAI Conference on Artificial Intelligence, 2018. AR: 24.6%; h5: 56 (AAAI) C98. L. Zhou, Y. Zhou, J. J. Corso, R. Socher, and C. Xiong. End-to-end dense video captioning with masked transformer. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018. AR: 29.5%; h5: 158 (CVPR) C97. X. Sun, R. Szeto, and J. J. Corso. A Temporally-Aware Interpolation Network for Video

4 of 27 Frame Inpainting. In Proceedings of Asian Conference on Computer Vision (ACCV), 2018. AR: 28%; h5: 30 (ACCV) C96. L. Zhou, N. Louis, and J. J. Corso. Weakly-supervised video object grounding from text by loss weighting and object interaction. In Proceedings of British Machine Vision Conference, 2018. AR: 30%; h5: 42 (BMCV) C95. K. R. Keane and J. J. Corso. The wrong tool for inference — a critical view of gaussian graph- ical models. In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods, 2018. AR∗: 50%; h5: 12 (ICPRAM) 2017 C94. R. Szeto and J. J. Corso. Click-here: Human-localized keypoints as guidance for viewpoint estimation. In Proceedings of IEEE International Conference on Computer Vision, 2017. AR: 28.9%; h5: 89 (ICCV) C93. Y. Yan, C. Xu, D. Cai, and J. J. Corso. Weakly supervised actor-action segmentation via robust multi-task ranking. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2017. AR: 28%; h5: 140 (CVPR) C92. L. Zhou, C. Xu, P. Koch, and J. J. Corso. Watch what you just said: Image captioning with text-conditional attention. In Proceedings of the Thematic Workshops of ACM Multimedia, 2017. (ACMMMW) 2016 C91. V. Dhiman, Q.-H. Tran, J. J. Corso, and M. Chandraker. A continuous occlusion model for road scene understanding. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2016. AR∗: 25%; h5: 128 (CVPR) C90. C. Xu and J. J. Corso. Actor-action semantic segmentation with grouping-process models. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2016. AR∗: 25%; h5: 128 (CVPR) C89. W. Ding, M. R. Ganesh, R. N. Severinghaus, J. J. Corso, and D. Panagou. Real-time model predictive control for keeping a quadrotor vehicle on the camera field-of-view of a ground robot. In Proceedings of the American Control Conference, 2016. AR∗: 50%; h5: 43 (ACC) C88. L. Zhao, D. Chan, Z. Chen, X. Wang, N. Paliwal, J. Xiang, H. Meng, J. J. Corso, and J. Xu. Rapid virtual stenting for intracranial aneurysms. In Proceedings of SPIE Conference on Medical Imaging, 2016. h5: 56 (SPIE) 2015 C87. W. Chen and J. J. Corso. Action detection by implicit intentional motion clustering. In Proceedings of IEEE International Conference on Computer Vision, 2015. AR: 30.3%; h5: 68 (ICCV) C86. C. Xu, S.-H. Hsieh, C. Xiong, and J. J. Corso. Can humans fly? Action understanding with multiple classes of actors. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2015. AR∗: 25%; h5: 118 (CVPR) C85. J. Lu, R. Xu, and J. J. Corso. Human action segmentation with hierarchical supervoxel consistency. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2015. AR∗: 25%; h5: 118 (CVPR) C84. R. Xu, C. Xiong, W. Chen, and J. J. Corso. Jointly modeling deep video and compositional text to bridge vision and language in a unified framework. In Proceedings of AAAI Conference on Artificial Intelligence, 2015. AR: 27%; h5: 37 (AAAI) 2014 C83. S. Kumar, V. Dhiman, and J. J. Corso. Learning compositional sparse models of bimodal percepts. In Proceedings of AAAI Conference on Artificial Intelligence, 2014. AR: 28%; h5: 41 (AAAI) C82. C. Xiong, S. McCloskey, and J. J. Corso. Latent domains for visual domain adaptation. In Proceedings of AAAI Conference on Artificial Intelligence, 2014. AR: 28%; h5: 41 (AAAI) C81. W. Chen, C. Xiong, R. Xu, and J. J. Corso. Actionness ranking with lattice conditional ordinal random fields. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2014. AR: 29%; h5: 106 (CVPR) C80. A. Barbu, D. Barrett, W. Chen, N. Siddharth, C. Xiong, J. J. Corso, C. D. Fellbaum, C. Hanson, S. J. Hanson, S. Helie,´ E. Malaia, B. A. Pearlmutter, J. M. Siskind, T. M. Talavage, and R. B. Wilbur. Seeing is worse than believing: Reading people’s minds better than computer-vision methods recognize actions. In Proceedings of European Conference on Computer Vision, 2014. AR: 24%; h5: 59 (ECCV) C79. V. Dhiman, A. Kundu, F. Dellaert, and J. J. Corso. Modern MAP inference methods for

5 of 27 accurate and faster occupancy grid mapping on higher order factor graphs. In Proceedings of International Conference on Robotics and Automation, 2014. AR: 48%; h5: 55 (ICRA) C78. S. Kumar, M. S. Narayanan, P. Singhal, J. J. Corso, and V. Krovi. Surgical tool attributes from monocular video. In Proceedings of IEEE International Conference on Robotics and Automation, 2014. AR: 48%; h5: 55 (ICRA) C77. C. Xiong, W. Chen, G. Chen, D. Johnson, and J. J. Corso. Adaptive quantization: An information-based approach to learning binary codes. In Proceedings of SIAM International Conference on Data Mining, 2014. AR∗: 15%; h5: 33 (SDM) C76. G. A. Gross, D. R. Schlegel, J. J. Corso, J. Llinas, R. Nagi, and S. C. Shapiro. Systemic test and evaluation of a hard+soft information fusion framework: Challenges and current approaches. In Proceedings of International Conference on Information Fusion, 2014. (FUSION) 2013 C75. C. Xu, S. Whitt, and J. J. Corso. Flattening supervoxel hierarchies by the uniform entropy slice. In Proceedings of the IEEE International Conference on Computer Vision, 2013. AR∗: 20%; h5: 60 (ICCV) C74. C. Xu, R. F. Doell, S. J. Hanson, C. Hanson, and J. J Corso. Are actor and action semantics retained in video supervoxel segmentation? In Proceedings of IEEE International Conference on Semantic Computing, 2013. AR∗: 30% (ICSC) C73. V. Dhiman, J. Ryde, and J. J. Corso. Mutual localization: Two camera relative 6-dof pose estimation from reciprocal fiducial observation. In Proceedings of International Conference on Intelligent Robots and Systems, 2013. AR∗: 43%; h5: 40 (IROS) C72. S. Kumar, M. Narayanan, P. Singhal, J. J. Corso, and V. Krovi. Product of tracking experts for surgical tool visual tracking. In IEEE Conference on Automation Science and Engineering, 2013. h5: 13 (CASE) C71. L. Zhao, W. Wu, and J. J. Corso. Semi-automatic brain tumor segmentation by constrained MRFs using structural trajectories. In Proceedings of and Computer Aided Intervention, 2013. AR∗: 30%; h5: 30 (MICCAI) C70. P. Das, C. Xu, R. F. Doell, and J. J. Corso. A thousand frames in just a few words: Lingual description of videos through latent topics and sparse object stitching. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2013. AR∗: 25%; h5: 106 (CVPR) C69. D. M. Johnson, C. Xiong, J. Gao, and J. J. Corso. Comprehensive cross-hierarchy cluster agreement evaluation. In Proceedings of AAAI Conference on Artificial Intelligence (Late-Breaking Papers Track), 2013. AR: 43%; h5: 41 (AAAI) C68. C. Xiong, D. M. Johnson, and J. J. Corso. Uncertainty reduction for active image clustering via a hybrid global-local uncertainty model. In Proceedings of AAAI Conference on Artificial Intelligence (Late-Breaking Papers Track), 2013. AR: 43%; h5: 41 (AAAI) C67. N. Coffee, J. Gawley, C. W. Forstall, W. J. Scheirer, D. Johnson, J. J. Corso, and B. Parks. Mod- elling the interpretation of literary allusion with machine learning techniques. In Proceedings of Digital Humanities, 2013. (DH) C66. P. Das, R. K. Srihari, and J. J. Corso. Translating related words to videos and back through latent topics. In Proceedings of Sixth ACM International Conference on Web Search and Data Mining, 2013. AR: 19%; h5: 48 (WSDM) C65. J. A. Delmerico, D. Baran, P. David, J. Ryde, and J. J. Corso. Ascending stairway modeling from dense depth imagery for traversability analysis. In Proceedings of IEEE International Conference on Robotics and Automation, 2013. AR∗: 45%; h5: 55 (ICRA) C64. R. S. Alomari, J. J. Corso, V. Chaudhary, and G. Dhillon. Lumbar spine disc herniation diagnosis with a joint shape model. In Proceedings of Medical Image Computing and Computer Aided Intervention Workshop on Computational Spine Imaging, 2013. (MICCAIW) 2012 C63. C. Xu, C. Xiong, and J. J. Corso. Streaming hierarchical video segmentation. In Proceedings of European Conference on Computer Vision, 2012. AR∗: 26%; h5: 66 (ECCV) C62. J. Ryde and J. J. Corso. Fast voxel maps with counting bloom filters. In Proceedings of International Conference on Intelligent Robots and Systems, 2012. AR∗: 43%; h5: 40 (IROS) C61. J. A. Delmerico, J. J. Corso, D. Baran, P. David, and J. Ryde. Ascending stairway modeling: A first step toward autonomous multi-floor exploration. In Proceedings of IEEE/RSJ Intelligent Robots and Systems (Video Proceedings), 2012. AR∗: 43%; h5: 40 (IROS) C60. C. Xiong, D. Johnson, R. Xu, and J. J. Corso. Random forests for metric learning with implicit

6 of 27 pairwise position dependence. In Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2012. AR∗: 18%; h5: 67 (KDD) C59. S. Sadanand and J. J. Corso. Action bank: A high-level representation of activity in video. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2012. AR∗: 25%; h5: 106 (CVPR) C58. C. Xu and J. J. Corso. Evaluation of super-voxel methods for early video processing. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2012. AR∗: 25%; h5: 106 (CVPR) C57. P. Agarwal, S. Kumar, J. Ryde, J. J. Corso, and V. N. Krovi. Estimating human dynamics on-the-fly using monocular video for pose estimation. In Proceedings of Robotics Science and Systems, 2012. AR∗: 20%; h5: 29 (RSS) C56. R. Xu, P. Agarwal, S. Kumar, V. N. Krovi, and J. J. Corso. Combining skeletal pose with local motion for human activity recognition. In Proceedings of VII Conference on Articulated Motion and Deformable Objects, 2012. h5: 9 (AMDO) C55. G. Chen, C. Xiong, and J. J. Corso. Dictionary transfer for image denoising via domain adaptation. In Proceedings of IEEE International Conference on Image Processing, 2012. AR∗: 45%; h5: 34 (ICIP) C54. K. R. Keane and J. J. Corso. Maintaining prior distributions across evolving eigenspaces: An application to portfolio construction. In Proceedings of 11th International Conference on Machine Learning and Applications, 2012. AR∗: 40%; h5: 12 (ICMLA) C53. C. Xiong and J. J. Corso. Coaction discovery: Segmentation of common actions across mul- tiple videos. In Proceedings of Multimedia Data Mining Workshop in Conjunction with the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (MDMKDD), 2012. (MDMKDD) C52. C. Xiong, D. Johnson, and J. J. Corso. Spectral active clustering via purification of the k- nearest neighbor graph. In Proceedings of European Conference on Data Mining, 2012. AR: 14% (ECDM) C51. C. Xiong, D. Johnson, and J. J. Corso. Efficient max-margin metric learning. In Proceedings of European Conference on Data Mining, 2012. Winner of Best Paper Award at ECDM 2012.. AR: 14% (ECDM) C50. K. R. Keane and J. J. Corso. Dynamically mixing dynamic linear models with applications in finance. In Proceedings of International Conference on Pattern Recognition Applications and Methods, 2012. (ICPRAM) C49. M. A. Bustamante and J. J. Corso. Using probabilistic ontologies for video exploration. In Proceedings of the Eighteenth Americas Conference on Information Systems, 2012. (AMCIS) C48. P. Agarwal, S. Kumar, J. Ryde, J. J. Corso, and V. N. Krovi. An optimization based framework for human pose estimation in monocular videos. In Proceedings of International Symposium on Visual Computing, 2012. (ISVC) 2011 C47. J. A. Delmerico, P. David, and J. J. Corso. Building facade detection, segmentation, and pa- rameter estimation for mobile robot localization and guidance. In Proceedings of International Conference on Intelligent Robots and Systems, 2011. AR∗: 43%; h5: 40 (IROS) C46. P. Agarwal, S. Kumar, J. J. Corso, and V. N. Krovi. Estimating dynamics on-the-fly using monocular video. In Proceedings of 4th Annual Dynamic Systems and Control Conference, 2011. (DSCC) C45. D. Gagneja, C. Xiong, and J. J. Corso. Towards a parts-based approach to sub-cortical brain structure parsing. In Proceedings of SPIE Conference on Medical Imaging, 2011. h5: 56 (SPIE) C44. A. Y. C. Chen and J. J. Corso. Temporally consistent multi-class video-object segmentation with the video graph-shifts . In Proceedings of the 2011 IEEE Workshop on Motion and Video Computing, 2011. (WMVC) C43. D. R. Schlegel, A. Y. C. Chen, C. Xiong, J. A. Delmerico, and J. J. Corso. AirTouch: Interacting with computer systems at a distance. In Proceedings of IEEE Winter Vision Meetings: Workshop on Applications of Computer Vision (WACV), 2011. h5: 16 (WACV) 2010 C42. W. Ceusters, J. J. Corso, Y. Fu, M. Petropoulos, and V. Krovi. Introducing ontological re- alism for semi-supervised detection and annotation of operationally significant activity in surveillance videos. In Proceedings of the 5th International Conference on Semantic Technologies for Intelligence, Defense and Security (STIDS), 2010. (STIDS)

7 of 27 C41. R. S. Alomari, J. J. Corso, V. Chaudhary, and G. Dhillon. Lumbar disc herniation cad with a GVF-snake model. In Proceedings of the 24th International Conference on Computer Aided Diagnosis and Surgery (CARS ’10), 2010. (CARS) C40. M. R. Malgireddy, J. J. Corso, S. Setlur, V. Govindaraju, and D. Mandalapu. A framework for hand gesture recognition and spotting using sub-gesture modeling. In Proceedings of the 20th International Conference on Pattern Recognition, 2010. AR∗: 55%; h5: 31 (ICPR) C39. Y. Tang, S. Srihari, H. Kasiviswanathan, and J. J. Corso. Footwear print retrieval system for real crime scene marks. In Proceedings of International Workshop on Computational Forensics, 2010. (IWCF) C38. A. Y. C. Chen and J. J. Corso. On the effects of normalization in adaptive MRF hierarchies. In Proceedings of CompImage ’10—Computational Modeling of Objects Presented in Images, 2010. C37. R. S. Alomari, J. J. Corso, V. Chaudhary, and G. Dhillon. Automatic diagnosis of lumbar disc herniation using shape and appearance features from mri. In Proceedings of SPIE Conference on Medical Imaging, 2010. h5: 56 (SPIE) 2009 C36. R. Rodrigues, G. Schroeder, J. J. Corso, and V. Govindaraju. Unconstrained face recognition using MRF priors and manifold traversing. In Proceedings of IEEE International Conference on Biometrics: Theory, Applications, Systems, 2009. AR∗: 43% h5: 25 (BTAS) C35. Y. Tao, L. Lu, M. Dewan, A. Y. C. Chen, J. J. Corso, J. Xuan, M. Salganicoff, and A. Krishnan. Multi-level ground glass nodule detection and segmentation in ct lung images. In Proceedings of Medical Image Computing and Computer Aided Intervention (MICCAI), volume LNCS 5762, pages 715–723, 2009. AR∗: 30%; h5: 30 (MICCAI) C34. T. J. Burns and J. J. Corso. Robust unsupervised segmentation of degraded document im- ages with topic models. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2009. AR∗: 25%; h5: 106 (CVPR) C33. R. S. Alomari, J. J. Corso, V. Chaudhary, and G. Dhillon. Desiccation diagnosis in lumbar discs from clinical mri with a probabilistic model. In Proceedings of 2009 IEEE International Symposium on Biomedical Imaging, 2009. AR∗: 60%; h5: 27 (ISBI) C32. H. Z. Girgis, J. J. Corso, and D. Fischer. On-line hierarchy of general linear models for selecting and ranking the best predicted protein structures. In Proceedings of IEEE Conference on Engineering in Medicine and Biology, volume 1, pages 4949–4953, 2009. h5: 28 (EMBS) C31. R. S. Alomari, J. J. Corso, V. Chaudhary, and G. Dhillon. Abnormality detection in lumbar discs from clinical mr images with a probabilistic model. In Proceedings of 23rd International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS 2009), 2009. (CARS) C30. P. Noel,¨ J. Xu, K. R. Hoffmann, and J. J. Corso. Geometric tomography: a limited-view approach for computed tomography. In Proceedings of the 25th Annual Symposium on Compu- tational Geometry, 2009. AR∗: 28% (ASCG) C29. C. S. Hoeflich and J. J. Corso. Segmentation of 2D Gel Electrophoresis Spots using a Markov Random Field. In Proceedings of SPIE Conference on Medical Imaging, 2009. h5: 56 (SPIE) C28. S. Seshamani, M. D. Smith, J. J. Corso, M. O. Filipovich, A. Natarajan, and G. D. Hager. Direct Global Adjustment Methods for Endoscopic Mosaicking. In Proceedings of SPIE Conference on Medical Imaging, 2009. h5: 56 (SPIE) C27. P. B. Noel,¨ J. J. Corso, J. Xu, K. R. Hoffmann, S. Schafer, and A. Walczak. Reconstruction from a Flexible Number of Projections in Cone-Beam Computed Tomography via Active Shape Models. In Proceedings of SPIE Conference on Medical Imaging, 2009. h5: 56 (SPIE) C26. P. B. Noel,¨ J. Xu, K. R. Hoffmann, J. J. Corso, S. Schafer, and A. Walczak. High Contrast Artifact Reduction in Cone Beam Computed Tomography by Using Geometric Techniques. In Proceedings of SPIE Conference on Medical Imaging, 2009. h5: 56 (SPIE) 2008 C25. A. Y. C. Chen, J. J. Corso, and L. Wang. HOPS: Efficient region labeling using higher order proxy neighborhoods. In Proceedings of International Conference on Pattern Recognition, 2008. AR∗: 55%; h5: 31 (ICPR) C24. J. Li, S. Tulyakov, F. Farooq, J. J. Corso, and V. Govindaraju. Integrating minutiae based fingerprint matching with local mutual information. In Proceedings of International Conference on Pattern Recognition, 2008. AR∗: 55%; h5: 31 (ICPR) C23. J. J. Corso, R. S. Alomari, and V. Chaudhary. Lumbar disc localization and labeling with a probabilistic model on both pixel and object features. In Proceedings of Medical Image Com- puting and Computer Aided Intervention (MICCAI), volume LNCS 5241 Part 1, pages 202–210, 8 of 27 2008. AR∗: 30%; h5: 30 (MICCAI) C22. I. Nwogu and J. J. Corso. Exploratory identification of image-based bio-markers for solid mass pulmonary tumors. In Proceedings of Medical Image Computing and Computer Aided Inter- vention (MICCAI), volume LNCS 5241, Part 1, pages 612–619, 2008. AR∗: 30%; h5: 30 (MICCAI) C21. J. J. Corso. Discriminative Modeling by Boosting on Multilevel Aggregates. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2008. AR∗: 25%; h5: 106 (CVPR) C20. J. J. Corso, A. Yuille, and Z. Tu. Graph-Shifts: Natural Image Labeling by Dynamic Hierarchi- cal Computing. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2008. AR∗: 25%; h5: 106 (CVPR) C19. I. Nwogu and J. J. Corso. (BP)2: Beyond Pairwise Belief Propagation, Labeling by Approxi- mating Kikuchi Free Energies. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2008. AR∗: 25%; h5: 106 (CVPR) C18. J. J. Corso, Z. Tu, and A. Yuille. MRF Labeling with a Graph-Shifts Algorithm. In Proceedings of International Workshop on Combinatorial Image Analysis, volume LNCS 4958, pages 172–184, 2008. (IWCIA) C17. I. Nwogu and J. J. Corso. Labeling irregular graphs with belief propagation. In Proceedings of International Workshop on Combinatorial Image Analysis, volume LNCS 4958, pages 295–305, 2008. (IWCIA) C16. P. B. Noel,¨ A. Walczak, K. R. Hoffmann, J. Xu, J. J. Corso, and S. Schafer. Clinical Evalua- tion of GPU-Based Cone Beam Computed Tomography. In Proceedings of High-Performance Medical Image Computing and Computer-Aided Intervention (HP-MICCAI), 2008. C15. S. Dube, J. J. Corso, A. Yuille, T. F. Cloughesy, S. El-Saden, and U. Sinha. Hierarchical Seg- mentation of Malignant Gliomas Via Integrated Contextual Filter Response. In Proceedings of SPIE Conference on Medical Imaging, 2008. h5: 56 (SPIE) 2007 C14. J. J. Corso, A. L. Yuille, N. L. Sicotte, and A. Toga. Detection and Segmentation of Patho- logical Structures by the Extended Graph-Shifts Algorithm. In Proceedings of Medical Image Computing and Computer Aided Intervention (MICCAI), 2007. AR∗: 30%; h5: 30 (MICCAI) C13. J. J. Corso, Z. Tu, A. Yuille, and A. W. Toga. Segmentation of Sub-Cortical Structures by the Graph-Shifts Algorithm. In Proceedings of Information Processing in Medical Imaging (IPMI), volume LNCS 4584, pages 183–197, 2007. AR: 28%; h5: 16 (IPMI) 2006 C12. J. J. Corso, E. Sharon, and A. L. Yuille. Multilevel Segmentation and Integrated Bayesian Model Classification with an Application to Brain Tumor Segmentation. In Proceedings of Medical Image Computing and Computer Aided Intervention (MICCAI), volume 2, pages 790– 798, 2006. AR∗: 30%; h5: 30 (MICCAI) 2005 C11. J. J. Corso and G. D. Hager. Coherent Regions for Concise and Stable Image Description. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, volume 2, pages 184–190, 2005. AR∗: 25%; h5: 106 (CVPR) 2004 C10. J. J. Corso, M. Dewan, and G. D. Hager. Image Segmentation Through Energy Minimization Based Subspace Fusion. In Proceedings of 17th International Conference on Pattern Recogntion (ICPR 2004), 2004. AR∗: 55%; h5: 31 (ICPR) C9. W. W. Lau, N. A. Ramey, J. J. Corso, N. Thakor, and G. D. Hager. Stereo-Based Endoscopic Tracking of Cardiac Surface Deformation. In Proceedings of Seventh International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2004. AR∗: 30%; h5: 30 (MICCAI) C8. N. Ramey, J. J. Corso, W. W. Lau, D. Burschka, and G. D. Hager. Real Time 3D Surface Tracking and Its Applications. In Proceedings of Workshop on Real-time 3D Sensors and Their Use (at CVPR 2004), 2004. (CVPRW) C7. G. Ye, J. J. Corso, and G. D. Hager. Gesture Recognition Using 3D Appearance and Motion Features. In Proceedings of Workshop on Real-time Vision for Human-Computer Interaction (at CVPR 2004), 2004. (CVPRW) 2003 C6. G. Ye, J. J. Corso, G. D. Hager, and A. M. Okamura. VisHap: Augmented Reality Combin- ing Haptics and Vision. In Proceedings of IEEE International Conference on Systems, Man and Cybernetics, 2003. h5: 20 (SMC) C5. J. J. Corso, D. Burschka, and G. D. Hager. Direct Plane Tracking in Stereo Image for Mobile 9 of 27 Navigation. In Proceedings of International Conference on Robotics and Automation, 2003. AR∗: 45%; h5: 55 (ICRA) C4. G. Ye, J. J. Corso, D. Burschka, and G. D. Hager. VICs: A Modular Vision-Based HCI Frame- work. In Proceedings of 3rd International Conference on Computer Vision Systems, pages 257–267, 2003. AR: 40%; h5: 15 (ICVS) C3. J. J. Corso, D. Burschka, and G. D. Hager. The 4DT: Unencumbered HCI With VICs. In Proceedings of CVPRHCI, 2003. (CVPRW) 2002 C2. J. Leven, J. J. Corso, J. D. Cohen, and S. Kumar. Interactive Visualization of Unstructured Grids Using Hierarchical 3D Textures. In Proceedings of IEEE/SIGGRAPH Symposium on Vol- ume Visualization and Graphics 2002, pages 37–44, 2002. (VOLVIS) C1. J. J. Corso, J. Chhugani, and A. Okamura. Interactive Haptic Rendering of Deformable Surfaces Based on the Medial Axis Transform. In Eurohaptics, pages 92–98, 2002.

Book Chapters and Theses B5. L. Zhao, Z. Peng, K. Finkler, A. Jerebko, J. J. Corso, and X. S. Zhou. Automatic collimation detection in digital radiographs with the directed hough transform and learning-based edge detection. In Patch-Based Techniques in Medical Imaging (LNCS 9467), pages 71–78. Springer International Publishing, 2015. B4. S. Dube, J. J. Corso, T. F. Cloughesy, S. El-Saden, A. Yuille, and U. Sinha. Data Mining Systems Analysis and Optimization in Biomedicine, chapter Automated MR Image Processing and Analysis of Malignant Brain Tumors: Enabling Technology for Data Mining. American Institute of Physics, 2007. B3. J. J. Corso. Techniques for Vision-Based Human-Computer Interaction. PhD thesis, The Johns Hopkins University, 2005. B2. G. Ye, J. J. Corso, and G. D. Hager. Real-Time Vision for Human-Computer Interaction, chapter 7: Visual Modeling of Dynamic Gestures Using 3D Appearance and Motion Features, pages 103–120. Springer-Verlag, 2005. B1. J. J. Corso. Vision-Based Techniques for Dynamic, Collaborative Mixed-Realities. In B. J. Thompson, editor, Research Papers of the Link Foundation Fellows, volume 4. University of Rochester Press, 2004. Invited Report for Link Foundation Fellowship.

Reports (Not Peer-Reviewed) R23. A. Venkataraman, B. Griffin, and J. J. Corso. Learning kinematic descriptions using spare: Simulated and physical ARticulated extendable dataset. Technical Report 1803.11147, ARXIV, 2018. R22. V. Dhiman, S. Banerjee, B. Griffin, J. M. Siskind, and J. J. Corso. A critical investigation of deep reinforcement learning for navigation. Technical Report 1802.02274, ARXIV, 2018. R21. S. Patel, B. Griffin, K. Kusano, and J. J. Corso. Predicting future lane changes of other highway vehicles using rnn-based deep models. Technical Report 1801.04340, ARXIV, 2018. R20. M. R. Ganesh, E. Hofesmann, B. Min, N. Gafoor, and J. J. Corso. T-recs: Training for rate-invariant embeddings by controlling speed for action recognition. Technical Report 1803.08094, ARXIV, 2018. R19. E. Hofesmann, M. R. Ganesh, and J. J. Corso. M-PACT: An open source platform for repeat- able activity classification research. Technical Report 1804.05879, ARXIV, 2018. R18. M. El Banani and J. J. Corso. Adviser networks: Learning what question to ask for human- in-the-loop viewpoint estimation. Technical Report 1802.01666, ARXIV, 2018. R17. R. Szeto, S. Stent, G. Ros, and J. J. Corso. A dataset to evaluate the representations learned by video prediction models. Technical report, ICLR Workshops, 2018. R16. S. Kumar, V. Dhiman, M. R. Ganesh, and J. J. Corso. Spatiotemporal articulated models for dynamic slam. Technical Report 1604.03526, arXiv, 2016. R15. J. J. Corso, A. Alahi, K. Grauman, G. D. Hager, L.-P. Morency, H. Sawhney, Y. Sheikh. Video Analysis for Body-worn Cameras in Law Enforcement. CCC Whitepaper. 2015. R14. A. Barbu, N. Siddharth, C. Xiong, J. J. Corso, C. D. Fellbaum, C. Hanson, S. J. Hanson, S. Helie,´ E. Malaia, B. A. Pearlmutter, J. M. Siskind, T. M. Talavage, and R. B. Wilbur. The compositional natural of verb and argument representations in the human brain. Technical Report 1306.2293, arXiv, 2013. 10 of 27 R13. C. S. Lea and J. J. Corso. Efficient hierarchical markov random fields for object detection on a mobile robot. Technical Report 1111.1599v1, arXiv, November 2011. R12. A. Perera, S. Oh, M. Leotta, I. Kim, B. Byun, C.-H. Lee, S. McCloskey, J. Liu, B. Miller, Z. F. Huang, A. Vahdat, W. Yang, G. Mori, K. Tang, D. Koller, L. Fei-Fei, K. Li, G. Chen, J. J. Corso, Y. Fu, and R. K. Srihari. GENIE TRECVID2011 multimedia event detection: Late- fusion approaches to combine multiple audio-visual features. In NIST TRECVID Workshop, 2011. R11. A. Y. C. Chen and J. J. Corso. Propagating multi-class pixel labels throughout video frames. In Proceedings of Western New York Image Processing Workshop, 2010. R10. J. A. Delmerico, J. J. Corso, and P. David. Boosting with stereo features for building facade detection on mobile platforms. In Proceedings of Western New York Image Processing Workshop, 2010. R9. H. Girgis and J. J. Corso. STP: The Sample-Train-Predict Algorithm and Its Application to Protein Structure Meta-Selection. Technical Report 2008-16, University at Buffalo SUNY, 2008. R8. I. Nwogu, J. J. Corso, and T. Bittner. The design of an ontology-enhanced anatomy labeler. Technical Report 2008-09, University at Buffalo SUNY, 2008. R7. C. Arnold, J. J. Corso, and A. Bui. An Unsupervised Approach to Automatic Image An- notation. In NSF Biomedical Informatics Workshop: Expanding Secondary Use of Health Data, 2007. R6. D. Burschka, G. Ye, J. J. Corso, and G. D. Hager. A Practical Approach for Integrating Vision- Based Methods into Interactive 2D/3D Applicationsa. Technical report, The Johns Hopkins University, 2005. CIRL Lab Technical Report CIRL-TR-05-01. R5. J. J. Corso, M. Dewan, and G. D. Hager. Image Segmentation Through Energy Minimization Based Subspace Fusion. Technical Report CIRL-TR-04-01, The Johns Hopkins University, 2004. R4. J. J. Corso, N. Ramey, and G. D. Hager. Stereo-Based Direct Surface Tracking with De- formable Parametric Models. Technical report, The Johns Hopkins University, 2003. CIRL Lab Technical Report 2003-02. R3. J. J. Corso, G. Ye, D. Burschka, and G. D. Hager. Software Systems for Vision-Based Spatial Interaction. In Proceedings of 2002 Workshop on Intelligent Human Augmentation and Virtual Environments, pages D–26 and D–56, 2002. R2. J. J. Corso and G. D. Hager. Planar Surface Tracking Using Direct Stereo. Technical report, The Johns Hopkins University, 2002. CIRL Lab Technical Report. R1. J. J. Corso and J. D. Cohen. Out-Of-Core Voxelization of Large Scalar Fields for Interactive Multiresolution Volume Rendering. Technical report, The Johns Hopkins University, 2002. Graphics Lab Technical Report.

Patents P6. K. D. Kusano, S. Patel, B. Griffin., J. J. Corso. System and Method for Vehicle Lane Change Prediction Using Structural Recurrent Neural Networks. (15/858,592). 12/2019 Notice of Allowance Received. P5. D. Likosky, S. Yule, F. Pagani, M. Mathis, J. J. Corso, R. Daglius, E. M. Provost. Automated Identification and Grading of Intraoperative Quality. Patent Pending (16/705,371) Submitted 2019. P4. J. Y. Song, S. Lemmer, J. J. Corso, W. S. Lasecki. Reconstructing 3D Video Using Particle Filtering to Aggregate Crowd Responses. Patent Pending (16/704,529) Submitted 2019. P3. J. J. Corso and S. Sadanand. Method of Recognizing Activity in Video. Patent Pending (WO/2013/122675) Submitted 2013. P2. D. Das, M. Filipovich, J. J. Corso, G. D. Hager. Systems and Methods for Motion and Dis- tance Measurement in Gastrointestinal Endoscopy. Patent Pending (13/457,305) Submitted 2013. P1. J. J. Corso, M. Smith, and M. Filipovich. System and Method for Mosaicing Endoscope Images Captured From Within A Cavity. Patent Pending (12/347,855) Submitted 2012.

11 of 27 Software & FiftyOne 2020 Data Sets Open-Source Tool for CV/ML dataset visualization, analysis and model debugging. https://github.com/voxel51/fiftyone Unified VLP 2020 Code to accompany our AAAI 2020 paper on unified video-language pretraining. https://github.com/LuoweiZhou/VLP Player51 2019 Open-Source Tool for efficient, web-based video rendering with CV/ML labels. https://github.com/voxel51/player51 BubbleNets 2019 Code to accompany our CVPR 2019 paper on intelligence selection of the frame to annotate in video object segmentation. https://github.com/griffbr/BubbleNets ETA 2018 Open-Source extensible toolkit for video analytics. https://github.com/voxel51/eta ViP 2019 Video software platform for object detection and action recognition based on PyTorch. https://arxiv.org/abs/1910.02793 https://github.com/MichiganCOG/ViP Grounded Video Description 2019 Code and Dataset to accompany our CVPR 2019 oral paper on grounded video description. Code: https://github.com/facebookresearch/grounded-video-description Data: https://github.com/facebookresearch/ActivityNet-Entities TASED-Net 2019 Code to accompany our ICCV 2019 paper on temporally-aggregating spatial encoder-decoder network for video saliency detection. https://github.com/MichiganCOG/TASED-Net M-PACT 2018 General purpose software framework for all video processing and activity recognition based on TensorFlow. https://arxiv.org/abs/1804.05879 https://github.com/MichiganCOG/M-PACT YouCook2 2017 Large-scale data set of third-person cooking videos categorized 89 recipes with each recipes having at least 21 unique instructional videos. Time-coded human-written recipes are provided along with the raw video. http://youcook2.eecs.umich.edu/ Click-Here CNNs 2017 Code to accompany our ICCV 2017 paper on human-in-the-loop inference for keypoint-based guidance of monocular viewpoint estimation. https://github.com/rszeto/click-here-cnn End-To-End Video Captioning 2016 Our system for end-to-end video captioning using text-conditional semantic attention. https://github.com/LuoweiZhou/e2e-gLSTM-sc Video2Text.net 2013 A website and web-service for automatic conversion of videos to natural language sentences based on the video content. This website showcases our work in the vision+language domain. http://www.video2text.net YouCook 2013 Data set of third-person cooking videos categorized into six styles of cooking and selected from open-source web videos of different kitchens and complexity levels. It contains object and action bounding boxes as well as multiple natural language descriptions of each video. http://web.eecs.umich.edu/~jjcorso/r/youcook Random Forest Distance 2012 Software implementation of our KDD 2012 tree-structured metric learning paper. http://web.eecs.umich.edu/~jjcorso/pubs/RFD_Package.zip LIBSVX 2012 12 of 27 Supervoxel library: a set of methods for early video processing by computing supervoxel segmen- tations as well as a quantitative benchmark for fair comparisons of those segmentations. http://web.eecs.umich.edu/~jjcorso/r/supervoxels Winner Best Demo Prize at 2nd Greater New York Multimedia and Vision Meeting. 6/2012 Winner Best Open Source Code 3rd Prize at IEEE CVPR 2012. 6/2012 Action Bank 2012 Code to compute a high-level feature representation of activity in video. http://web.eecs.umich.edu/~jjcorso/r/actionbank Winner Best Open Source Code 3rd Prize at IEEE CVPR 2012. 6/2012 Chen Xiph.org 2011 Data set to support video label propagation and video semantic segmentation. Contains 8 videos densely labeled (frame-by-frame) into the 21 MSRC classes. The videos are selected from the xiph.org repository. http://www.cse.buffalo.edu/~aychen/LabelPropagation/labelpropagation.zip Video Label Propagation 2011 Code to propagate an initial segmentation through a video sequence. http://www.cse.buffalo.edu/~aychen/LabelPropagation/propagatelabel.m MuleSeg 2006 Extensible software for multilevel segmentation of 2D and 3D images based on an extended Seg- mentation by Weighted Aggregation algorithm using the Bayesian model-aware affinity GUSTO 2002 System for interactive, hierarchical rendering of large (out-of-core) 3D scalar fields, including unstructured grids, structured grids, and voxels. Jointly with Joshua Leven, Jonathan D. Cohen, and Subodh Kumar. XVision2 2001 Modular software architecture for real-time vision development. Jointly with Gregory Hager, Darius Burschka, Sam Lang, and Xiangtian Dai.

Funding Total Funding: $19,783,349 ($12,172,629 as PI) Share Credit: $11,546,745 Funding is sorted by start date (recent first). Active funding (18, 25, 30, 31, 32, 34, 35, 36) is prefixed with an asterisk. Dollar amounts listed as $Total ($Share; Percent Credit) F36. *Co-I: Novel Assessments of Technical and Non-Technical $3,443,788 ($391,465; 11%) Cardiac Surgery Quality Source: NIH 12/2019–11/2024 Collaborators: Donald Likosky (MED, PI), Frank Pagani (MED, PI), Matthew Caldwell (MED), Sarah Krein (MED), Milisa Manojlovich (Nursing), Michael Mathis (MED), Min Zhang (Biostats), Steven Yule (BWH), Roger Dias (BWH) Objective: Advance the modeling and understanding of technical and non-technical char- acteristics that correlate with various surgical outcomes. F35. *Co-I: Interactive Learning for Manipulating Piles of Stuff $1,193,108 ($270,357; 23%) Source: TRI 7/2018–12/2020 Collaborators: Brent Griffin (ECE, PI), Dmitry Berenson (ECE) Objective: Investigate new methods for the intersection of computer vision and mobile manipulation, with an emphasis on interactively learning perceptual models. F34. *Co-PI: Human-Augmented Computer Vision for Robust 3D Scene $504,045 ($257,394; 51%) Reconstruction at Scale Source: TRI 1/2018–12/2020 Collaborators: Walter Lasecki (CSE) Objective: Understand how humans can be involved in the loop at inference time in a hybrid intelligence mindset to reconstruct complicated visual scenes from monocular data. F33. PI: TARDIS-V: Multi-Layer Compositional Activity Understanding $1,439,890 ($949,667; 66%) using Joint Visual and Semantic Inference Source: IARPA DIVA (sub to SRI) 10/2017–5/2021 Collaborators: Jia Deng (CSE) Objective: Investigate new methods for fine-grained human activity recognition in ground- level and first-person-view cameras. F32. *PI: BOCA: Body-Worn Camera Analytics $681,290 ($681,290; 100%) 13 of 27 Source: NIST PSIAP 6/2017–5/2019 Collaborators: Yan Tom Yan (Texas State University) Objective: Investigate new methods for transfer learning between third-person and first- person perspective human activity video. F31. *PI: SPIDER: Subspace Primitives that are Interpretable and Diverse $1,596,900 ($798,450; 50%) Source: DARPA D3M 4/2017–3/2021 Collaborators: Laura Balzano (ECE) Objective: Investigate new machine learning models and based on subspace primitive ideas and involving multimodal data sources and explicit invariance properties. F30. *PI: CI:New: COVE—Computer Vision Exchange for Data, $343,000 ($343,000; 100%) Annotation, and Tools Source: National Science Foundation (NSF) CRI 8/2016–7/2019 Collaborators: Kate Saenko (Boston University) and Walter Scheirer (Notre Dame) Objective: Develop a website that makes data and related resources openly and widely available to the computer vision research community. F29. Co-PI: Efficient Human-in-the-Loop Computer Vision Algorithms $199,810 ($89,915; 50%) to Create Datasets of Rare Traffic Events From Video Source: UM Mobility Transformation Center 1/2017–12/2017 Collaborators: Walter Lasecki (CSE) Objective: Investigate improved strategies for incorporating humans in the loop for monoc- ular reconstruction problems. F28. Co-PI: Task-Oriented Active Perception and Motion Planning $499,184 ($249,592; 50%) for Manipulating Piles of Stuff Source: Toyota Research Institute 1/2017–6/2018 Collaborators: Dmitry Berenson (ECE), Brent Griffin (ECE) Objective: Investigate tightly coupled active perception and planning strategies for interac- tive manipulation and task-oriented processing of assortments of objects in tabletop settings. F27. PI: MEDISPHERE $650,278 ($650,278; 100%) Source: DARPA MediFor (Sub from PAR Government) 9/2016–8/2018 Collaborators: Brent Griffin (ECE) Objective: Support the creation of manipulated video data for the forensics TA1 teams on the program. F26. PI: Computer Vision and Crowdsourcing for Vehicle Crash Analysis $138,324 ($69,162; 50%) Source: Denso 3/2016–8/2016 Collaborators: Walter Lasecki (CSE) Objective: Develop a system where human can operate in a monocular reconstruction loop with an emphasis on road scenes. F25. *PI: RobotSLANG: Simultaneous Localization, Mapping, $649,999 ($649,999; 100%) and Language Acquisition Source: National Science Foundation (NSF) NRI 9/2015–8/2020 Collaborators: Jeffrey Mark Siskind (Purdue ECE, Separate NSF Collaborative Grant) Objective: Generalize simultaneous localization and mapping to include language acquisi- tion for unknown environments and unknown symbol grounding functions. F24. Co-PI: Novel trans-synaptic tracers and computational tools for labeling $100,000 ($50,000; 50%) and automated reconstructing dense neural circuits at single cell resolution in the mouse brain Source: University of Michigan MiBrain Initiative 8/2015-7/2016 Objective: Integrate computer vision and machine learning tools to label, reconstruct and classify all the neurons that connect to a single subtype-defined neuron at single cell and single synapse resolution in the mouse brain. F23. PI: Blind Multibody Prediction with Semantic Dynamical Models $336,524 ($488,060; 100%) Source: Toyota 12/2015–2/2018 Objective: Model multibody dynamics to predict the safe egress time window for sensor- blind autonomous or assistive vehicles. F22. PI: Learning from Unconstrained Instructional Videos $100,000 ($50,000; 50%) with Structured and Sparse Models Source: Samsung GRO 10/2015–9/2016 Collaborators: Cornelia Fermuller (U Maryland, College Park, CS) Objective: To develop machine learning methods that can automatically learn the semantic 14 of 27 human-object relationships of temporal processes from unstructured web-videos. F21. PI: Action Co-Discovery As A Cross-Reconstruction Problem $290,481 ($290,481; 100%) Source: Army Research Office (ARO) 8/2015–7/2019 Objective: Formulate, solve and study the detection of common actions across multiple unsupervised videos as a cross-reconstruction problem. F20. PI: Vehicle Tethered Quadrotor Control $25,000 ($12,500; 50%) Source: TARDEC 3/2015–9/2015 Collaborators: Necmiye Ozay (ECE) and Dimitra Panagou (AERO) Objective: Determine the feasibility of GPS-denied control methods for tethered quadrotor operation from a vehicle. F19. PI: Pictorial Structures for Scene Context $620,000 ($620,000; 100%) Source: DARPA STTR (Sub from Soartech; Phases I & II) 3/2015–9/2019 Objective: Integrate the SOAR cognitive architecture and state of the art computer vision for improving robustness and efficiency in scene understanding. F18. *PI: Computational PB&J: Learning from Instructional Video $67,657 ($67,657; 100%) Source: Google Faculty Research Program 4/2015–4/2018 Objective: This project investigates the rich problem of learning visual- and language- grounded process models from instructional video content. F17. PI: CI-New: Collaborative Research: Federated Data Set $150,000 ($75,000; 50%) Infrastructure for Recognition Problems in Computer Vision Source: NSF Community Research Infrastructure 10/2014–10/2017 Collaborators: Kate Saenko (UMass Lowell, CS) Objective: This project seeks to establish a federated infrastructure for datasets and anno- tations within the computer vision community F16. PI: Transferring ACE to the Analyst $250,000 ($250,000; 100%) Source: DARPA CSSG Phase III 7/2012–7/2014 Objective: The main objective is to investigate how our developments in the Phase II active clustering into real application use with our defense partner. F15. PI: Computer Vision and Mobile Robot Technologies for $261,178 ($261,178; 100%) Advanced Emergency Response Source: CUBRC (Federal Highway Administration) 10/2011–3/2014 Objective: This project seeks to develop and deploy single and multiple robotic platforms capable of concurrently mapping emergency sites in normal and adverse conditions. F14. Co-PI: Objective Imaging-Based Assessment of Smoking Behavior $275,000 ($164,313; 60%) from Used Filters Source: National Institutes of Health NCI 1 R21 CA160825-01 9/2011–9/2014 Collaborators: O’Connor (PI, Roswell Park) Objective: The proposal seeks to refine our ability to quantify the smoking behavior through digital image analysis of cigarette filters. F13. PI: Two-Rank Mobile Robot Fleet for Swarm Surveillance, Warfighter $250,000 ($200,000; 80%) Assistance, and other Army-related Research and Research-Related Education Source: Army Research Office DURIP 9/2011-6/2013 Collaborators: Demirbas (CSE), Fu (CSE), Krovi (MAE), Nagi (MAE) Objective: The basic goal is to enhance the DoD’s capabilities for using fleets and swarms of ground-based sensor-rich unmanned and autonomous mobile robots (UGVs). F12. PI: GBS: Guidance By Semantics—Using High-Level Visual $150,000 ($150,000; 100%) Inference to Improve Vision-based Mobile Robot Localization Source: Army Research Office Young Investigator Program 6/2011-6/2014 Objective: The goal is to investigate how semantic perception can be used to improve the accuracy, speed, and robustness of vision-based localization of mobile robot platforms. F11. PI: Comprehensive Object Detection Library for Large-Scale $190,975 ($190,975; 100%) Image Analytics Source: Naval Postgraduate School 5/2011-10/2012 Objective: The goal of the proposed work is to build a comprehensive object detection library and evaluate the methods for large-scale image sets. F10. PI: Ontology, Event Agents and Event Recounting for ALADDIN $999,469 ($799,575; 80%)

15 of 27 Source: IARPA (sub from Kitware, Inc.) 3/2011-3/2016 Collaborators: Fu (CSE) and R. Srihari (CSE) Objective: The goal of this project is to improve the representation and indexing of objects and events in large-scale video analysis by efficiently encoding the low-level perceptual entities in the video and grounding them with rich high-level semantics. F9. PI: ISTARE: Intelligent Spatio-Temporal Activity Reasoning Engine $2,208,368 ($1,104,184; 50%) Source: DARPA Mind’s Eye Program 9/2010-12/2013 Collaborators: Fu (CSE), Ceusters (Psychiatry), Krovi (MAE), Petropoulos (CSE) Objective: The goal of this proposal is a development of a methodology for representation, learning, recognition of and reasoning over activities in persistent surveillance videos. F8. Co-PI: II-NEW: Acquisition of a Biomedical Computing Infrastructure $588,554 ($58,855; 10%) Source: National Science Foundation CRI 9/2010-9/2011 Collaborators: Chaudhary (PI, CSE), Hoffmann (NS), Krovi (MAE), Furlani (CCR) Objective: The major goal of this project is to establish a state-of-the-art computing infras- tructure for memory- and compute-bound problems in biomedicine. F7. PI: Semantic Video Summarization With Ontology-Driven $357,080 ($357,080; 100%) Probabilistic Inference on Massive Multimedia Collections Source: CIA/IC Postdoc Fellowship Program 7/2010-7/2013 Objective: The main goal of the proposal is to advance the understanding of how proba- bilistic ontologies of semantic entities and entity-entity relationships can drive inference for semantic summarization of content in massive video collections. F6. PI: ACE – Active Clustering for Exploitation and Defense Forensics $399,780 ($399,780; 100%) Source: DARPA CSSG Phase II 6/2010-6/2012 Objective: The main objective is to investigate how active clustering can be used to induce high-level models of phenomena in video with the help of a user. F5. PI: Digital Imaging of Cigarette Filters $27,958 ($27,958; 100%) Source: Health Research, Inc. 9/2009-12/2009 Objective: The major goal of this project is to develop improved image analysis techniques for quantifying the properties of cigarette filters in digital images.

F4. PI: CAREER: Generalized Image Understanding with Probabilistic $539,086 ($539,086; 100%) Ontologies and Dynamic Adaptive Graph Hierarchies Source: National Science Foundation CAREER Program 7/2009-7/2014 Objective: The major research goal is to investigate a unified model of image representation integrating probabilistic methods, machine learning, probabilistic ontologies, and dynamic adaptive graphs to advance our ability to solve the image understanding problem. F3. PI: Probabilistic Ontology Induction for Generalized Video Understanding $99,670 ($99,670; 100%) Source: DARPA CSSG Phase I 4/2009-7/2010 Objective: The major goal is to develop the foundational models for learning high-level semantic representations of objects from video data, automatically and unsupervisedly. F2. Co-PI: Multimodal Command-and-Control By Integrating $129,953 ($32,488; 25%) Two-Handed Gestures and Speech Source: Hewlett Packard Labs Innovation Research Program 8/2008-8/2010 Collaborators: Govindaraju (PI) Objective: The major goal of this project is to integrate multimodal processing into robust gesture recognition. F1. Co-PI: Reconstructing CT Images from a Limited Number of Projections $27,000 ($9,000; 33%) Source: UB Interdisciplinary Research Development Fund Collaborators: Xu (PI, CSE) and Hoffman (NS) Objective: This project explores how redundant information in different projections can be combined with a priori knowledge of the anatomy to reduce dosage while maintaining high quality reconstructions.

Affiliations Senior Member, Institute of Electrical and Electronics Engineers (IEEE) 2016-Present Member since 1998 Member, Association for the Advancement of Artifical Intelligence (AAAI) 2011-Present Member, Mathematical Association of America (MAA) 2005-Present 16 of 27 Member, IEEE Robotics and Automation Society 2003-2005 Member, Upsilon Pi Epsilon, Computer Science Honor Society 1999-Present Member, Alpha Sigma Nu, National Jesuit Honor Society 1999-Present Member, Association of Computing Machinery (ACM) 1998-Present Member, IEEE Computer Society (IEEE) 1998-Present

Service Editorships /Editorial Board Membership ∗ Associate Editor, IEEE Trans. on Pattern Analysis and Machine Intelligence 10/2014–12/2019 Published by IEEE ∗ Editorial Board Member, International Journal of Computer Vision 8/2014–3/2019 Published by Springer ∗ Associate Editor, Computer Methods and Programs in Biomedicine 9/2009–6/2014 Published by Elsevier

Conference /Workshop Chair ∗ General Chair, FIVER 2018: Fine-Grained Instructional Video Understanding Workshop (at CVPR 2018) 2018 Jointly with Ivan Laptev, Josef Sivic and Luowei Zhou ∗ General Chair, Midwest Computer Vision Workshop 2018 Jointly with Jia Deng ∗ General Chair, BigVision 2016: International Workshop on Large Scale Visual Recognition and Retrieval (at CVPR 2016) 2016 Jointly with Samy Bengio (Google) and Fei-Fei Li (Stanford) ∗ General Chair, The Future of Datasets in Vision 2015 (at CVPR 2015) 2015 Jointly with Kate Saenko

Senior Program Committee ∗ Area Chair, European Conference on Computer Vision (ECCV) 2020 ∗ Area Chair, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2019 ∗ Area Chair, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2017 ∗ Associate Editor, IEEE Intl. Conf. on Robotics and Automation (ICRA) 2017 ∗ Area Chair, AAAI Conference on Artificial Intelligence 2017 ∗ Area Chair, AAAI Conference on Artificial Intelligence 2016 ∗ Area Chair, IEEE Intl. Conf. on Computer Vision 2016 ∗ Associate Editor, IEEE Intl. Conf. on Robotics and Automation (ICRA) 2016 ∗ Program Chair, BigVision 2015: International Workshop on Large Scale Visual Recognition and Retrieval (at CVPR 2015) 2015 Jointly with O. Russakovsky (Stanford), J. Deng (Michigan) and Y. Lin (NEC) ∗ Associate Editor, IEEE Intl. Conf. on Robotics and Automation (ICRA) 2015 ∗ Program Chair, BigVision 2014: Intl. Workshop on Large Scale Visual Recognition and Retrieval (at CVPR 2014) 2014 Jointly with J. Deng (Michigan), A. Berg (UNC) and Y. Lin (NEC) ∗ Area Chair, European Conference on Computer Vision (ECCV) 2014 ∗ Area Chair, IEEE Winter Conf. on Applications of Computer Vision (WACV) 2014 ∗ Area Chair, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2013 ∗ Area Chair, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2012

Other Conference and Workshop Service ∗ Workshops Chair, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 ∗ Video Chair, IEEE International Conference on Computer Vision (ICCV) 2015 ∗ Organizing Committee, CONTACT 2014: First International Workshop on Computer vision + ONTology Applied Cross-disciplinary Technologies (at ECCV 2014) 2014 Jointly with M. Cristani (Universit`adegli Studi di Verona) and R. Ferrario (Italian National Research Council) ∗ Student Activities Chair, IEEE Conf. on Computer Vision and Pattern Recognition 2014 ∗ Organizing Committee, ACCV Workshop on Detection and Tracking in Challenging Environ- ments (DTCE 2012) 2012 Jointly with J. Lim (Hanyang Univ.), B. Han (POSTECH), B. Triggs (CNRS) and A. Elgammal (Rutgers). ∗ Student Activities Chair, IEEE Conf. on Computer Vision and Pattern Recognition 2012 ∗ Organizing Committee, Joint Workshop on High-Performance and Distributed 2011 Computing for Medical Imaging (HP-MICCAI/MICCAI-DCI) ∗ Organizing Committee, High-Performance MICCAI 2010 17 of 27 Jointly with Chaudhary (UB), Gong (IBM), Blezek (Mayo), and Kulikowski (Rutgers) ∗ Organizing Committee, High-Performance MICCAI 2008 Jointly with Chaudhary (UB) and Gong (IBM)

Program Committee and Conference Reviewer ∗ European Conference on Computer Vision ∗ IEEE Conference on Computer Vision and Pattern Recognition ∗ IEEE Conference on Robotics and Automation ∗ IEEE/RSJ International Conference on Intelligent Robots and Systems ∗ IEEE International Conference on Computer Vision ∗ International Conference on Multimedia and Expo ∗ Medical Image Computing and Computer Aided Intervention. Above, years are not given for readability; service has been steady for most of these since 2006. ∗ IEEE International Conference on Semantic Computing 2015 ∗ IEEE International Conference on Face and Gesture 2015 ∗ Graphical Models in Computer Vision (GMCV at ECCV 2014) 2014 ∗ IEEE International Workshop on Web-scale Vision and Social Media (VSM at CVPR 2014) 2014 ∗ IEEE International Conference on Semantic Computing (ICSC) 2014 ∗ International Workshop on Large Scale Visual Commerce (LSVisCom at ICCV) 2013 ∗ Workshop on Large-Scale Video Search and Mining (LSVSM’13 at ICCV) 2013 ∗ International Workshop on Action Recognition with a Large Number of Classes (at ICCV) 2013 ∗ ISPRS Workshop on Image Sequence Analysis (ISA) 2013 ∗ IEEE International Conference on Semantic Computing (ICSC) 2013 ∗ IEEE Workshop on Mobile Vision (at ICCV) 2013 ∗ IEEE Face and Gesture (FG) 2013 ∗ Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR) 2013 ∗ Fully 3D Image Reconstruction in Radiology and Nuclear Medicine Meeting 2013 ∗ Asian Conference on Computer Vision 2012 ∗ IEEE International Conference on Semantic Computing (ICSC) 2012 ∗ International Symposium on Visual Computing (ISVC) 2012 ∗ International Conference on Image Processing (ICIP) 2012 ∗ IEEE International Conference on Semantic Computing (ICSC) 2011 ∗ Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR) 2011 ∗ Int’l Workshop on Stochastic Image Grammars (SIG-11, at ICCV) 2011 ∗ IEEE International Conference on Semantic Computing (ICSC) 2010 ∗ IEEE Workshop on Mobile Vision (at ICCV) 2011 ∗ IEEE Workshop on Mobile Vision (at CVPR) 2010 ∗ Workshop on Probabilistic, Models for Medical Image Analysis (at MICCAI) 2009 ∗ Int’l Workshop on Stochastic Image Grammars (SIG-09, at CVPR 2009) 2009 ∗ Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR) 2009 ∗ IEEE 8th Intll Symposium on Signal Processing and Information Technology (ISSPIT) 2008 ∗ Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR) 2007 ∗ IEEE 7th Int’l Symposium on BioInformatics and BioEngineering (BIBE) 2007

Journal Reviewer ∗ ACM Computing Reviews ∗ Artificial Intelligence ∗ Computer Methods and Programs in Biomedicine ∗ Computer Vision and Image Understanding ∗ IEEE Multimedia ∗ IEEE Signal Processing Letters ∗ IEEE Transactions on Biomedical Engineering ∗ IEEE Transactions on Image Processing ∗ IEEE Transactions on Information Technology in Biomedicine ∗ IEEE Transactions on Knowledge and Data Engineering ∗ IEEE Transactions on Medical Imaging ∗ IEEE Transactions on Multimedia ∗ IEEE Transactions on Pattern Analysis and Machine Intelligence ∗ IEEE Transactions on Systems, Man, and Cybernetics ∗ Image and Vision Computing ∗ International Journal of Computer Assisted Radiology and Surgery ∗ International Journal of Computer Vision ∗ Journal of Mathematical Imaging and Vision ∗ Machine Vision and Applications

18 of 27 ∗ Medical Physics ∗ Neuro Image ∗ Pattern Recognition ∗ Pattern Recognition Letters ∗ Robotics and Autonomous Systems

Panelist ∗ National Institutes of Health 2015–16 ∗ National Science Foundation Panel/Reviewer (CISE/IIS) 2009,2011–13,2015–18 ∗ Technology Foundation STW 2009 A Dutch funding agency for academic research in the field of applied sciences

University of Michigan Committees ∗ ECE Strategic Vision Committee 1920 ∗ CoE Robotics Institute Executive Committee 1617–1819 ∗ UM Institutional Autonomous Systems Committee 1617–1718 ∗ MTC Internal Funding Review Panel 1516 ∗ ECE Graduate Advisor for Computer Vision 1516–Current ∗ CE Undergraduate Program Committee 1516–Current ∗ CE Undergraduate Advisor 1516–1617 ∗ CE Undergraduate Honors and Awards 1516–1819 ∗ MTC Internal Funding Review Panel 1415 ∗ ECE Graduate Admissions Committee 1415–Current ∗ CoE TRW Endowed Research Award Committee 1415 ∗ ECE Graduate Activities Committee 1415

SUNY at Buffalo Committees ∗ Rising Scholar Committee (advisor to VPR) 2013–2014 ∗ Faculty Search Committee 2010-2014 ∗ Graduate Studies Committee 2008-2014 ∗ Artificial Intelligence Area Coordinator 2011–2013 ∗ Distinguished Speaker Series Committee 2010 ∗ Brochure and Website Committee 2010 ∗ Colloquium Committee 2009 ∗ Graduate Admissions Committee 2008-2009

Invited Talks Toward Kinematic Reconstruction of Roadway Scenes from Monocular Video using Hybrid Intel- ligence - University of Bonn Computer Science 11/2019 - University of Michigan Automotive Research Center Symposium 9/2018 Are we using our humans best? A View From Video Object Segmentation - British Computer Society Video Understanding Symposium 9/2019 Academic Perspectives for Video Analytics in Public Safety - NIST/DHS VAPS 11/2018 Segmentation is Selection - ECCV Workshop on Video Segmentation 9/2018 - NCSU ECE Distinguished Lecture Series 10/2018 Computer Vision & Video Analytics – Bridging Academia and Startup - ACM SIGIR 7/2018 Computer Vision & Video Analytics in Large-Scale Public Safety - Disney Large Venue Public Safety Meeting 8/2017 Toward Automated Understanding of Instructional Videos - INRIA Paris 4/2017 - University of Trento 4/2017 - ECCV Workshop on Visual Storytelling and Large Scale Movie Description Challenge 10/2016 Sparse Modeling in Deep and Cross-Modal Embeddings - Carnegie Mellon University LTI Colloquium 1/2017 - Information Theory and Applications 1/2017 Grouping Process Models in Actor-Action Segmentation - ActivityNet Large Scale Activity Recognition Challenge at IEEE CVPR 6/2016 - Xerox PARC 5/2016 19 of 27 - INRIA Paris 5/2016 Cross-Modal Embeddings with Video, Text and Speech - University of Rochester, Data Science Institute 5/2016 - Rochester Institute of Technology, Center for Imaging Science 5/2016 - Information Theory and Applications 1/2016 - Large Scale Movie Description Challenge Workshop at IEEE ICCV 12/2015 - Language and Vision Workshop at IEEE CVPR 6/2015 Video Analysis for Body Worn Cameras - (Keynote) Moving Cameras Meet Video Surveillance Workshop at IEEE CVPR 2016 6/2016 - Computers, Freedom, Privacy 10/2015 Supervoxels in Multi-X Understanding of Dynamic Scenes - (Keynote) IEEE/ISPRS 3rd Joint Workshop on Multi-Sensor Fusion for Dynamic Scene Under- standing at IEEE CVPR 6/2015 Toward the Who and Where of Action Recognition - University of Maryland at College Park 9/2015 - INRIA Grenoble 7/2015 Perceiving Action in Space-Time: Computational and Human Perspectives - Michigan State University (CSE) 11/2014 - University of Michigan (EECS) 3/2014 - University of Minnesota (CSE) 3/2014 - Northeastern University (ECE) 2/2014 Why Label When You Can Compare? Active Constraint Pursuit in Metric Learning and Cluster- ing - Virginia Tech (CS) 3/2014 Semantic Scale Selection from Video Segmentation Hierarchies - Ohio State University (ECE) 1/2014 What Representation is Right for Recognizing Activities in the Large Scale? - Keynote Address at ICCV 2013 Workshop on Action Recognition 12/2013 with a Large Number of Classes Can Language and Segmentation Play a Role in Large Scale Video Search? - ICCV 2013 Workshop on Large Scale Video Search and Mining 12/2013 Advances in Segmentation for Video Understanding - Rutgers University (Perceptual Science Forum Keynote Address) 5/2013 - University of Central Florida 4/2013 - University of Massachusetts Amherst 2/2013 - Stevens Institute of Technology 12/2012 - University of Pennsylvania 11/2012 - Microsoft Research Asia 8/2012 Joint Segmentation and Recognition of Medical Images with Layered Models - Second Vision and Multimedia Meeting in the Greater NY Area 6/2012 Graph-Shifts: Dynamic Hierarchical Energy Minimization for Segmentation and Classification. - GE Research 10/2010 - University of California, San Diego, Computer Science and Engineering 9/2010 - Army Research Labs CISD 10/2010 - Johns Hopkins University, Computer Science 5/2009 - Siemens Medical Solutions 12/2008 - Massachusetts Institute of Technology, CSAIL 11/2008 - SUNY at Buffalo, Computer Science and Engineering 3/2007 Bayesian Machine Intelligence Research at Buffalo - ITT Space Systems Division 2/2009 - MTM Interactive 6/2008 Multilevel Image Segmentation and Integrated Bayesian Model Classification. - Stony Brook University, Computer Science 10/2006 - IBM TJ Watson Research Center 10/2006 - Rutgers University, Center for BioImaging and Modeling 10/2006 - Siemens Corporate Research 10/2006 - Vanderbilt Institute for Imaging Science 7/2006 - UCLA Laboratory of Neuroimaging SIG-STAT Meeting 3/2006

20 of 27 - UCLA Statistics Seminar Series 4/2006 - Johns Hopkins University, ERC CISST 5/2006 Coherent Image Regions - UCLA Medical Imaging Informatics 5/2005

Teaching Outreach and K12 Teaching AI Family Challenge 9/2018 Panel participant and mentor Lights, Pinhole and Lenses 6/2016, 6/2017 & 6/2018 U Michigan COE Xplore Program Reached 60 Middle Schoolers through 6 90 minute sessions over two days. Lights, Pinhole and Lenses: Computer Imaging 6/2015 U Michigan COE Xplore Program Reached 60 Middle Schoolers through 6 90 minute sessions over two days.

Tutorials and Summer Schools Machine Learning II (Ensemble Methods) 6/2015 U Michigan Big Data Summer Institute Lecture Video Segmentation Tutorial at CVPR 2014 6/2014 with Irfan Essa and Matthias Grundmann IPAM Graduate Summer School on Computer Vision 7/2013 University of California, Los Angeles, Institute for Pure and Applied Mathematics International Summer School on Vision, Learning and Cognition 8/2012 Beijing University of Posts and Telecommunications

University of Michigan,Electrical Engineering and Computer Science EECS 542 Advanced Topics in Computer Vision - Winter 2017: Enrollment 75 - Winter 2016: Enrollment 18 EECS 504 Foundations of Computer Vision - Fall 2020: Enrollment: 130 - Fall 2018: Enrollment: 67 - Winter 2018: Enrollment 78 - Fall 2016: Enrollment 64 - Fall 2015 (as 598): Enrollment 41 - Fall 2014 (as 598): Enrollment 46 EECS 598 Probabilistic Graphical Models - Winter 2015: Enrollment 36 EECS 442 Computer Vision - Fall 2018: Enrollment 111 - Fall 2017: Enrollment 89

SUNY at Buffalo,Computer Science and Engineering CSE 455/555 Introduction to Pattern Recognition Cross-listed undergraduate graduate course. - Spring 2013: Enrollment 70 - Spring 2012: Enrollment 73 - Spring 2011: Enrollment 60 - Spring 2010: Enrollment 35 - Spring 2009: Enrollment 29 CSE 672 Bayesian Vision New upper-level graduate course. - Fall 2012: Enrollment 22 - Fall 2010: Enrollment 12 - Spring 2009: Enrollment 8 CSE 642 Techniques in AI: Vision for HCI - Fall 2009: Enrollment 8 CSE Seminars

21 of 27 - Spring 2014: Readings in Joint Visual, Lingual and Physical Models and Inference - Fall 2011: Readings in Computer Vision and Machine Learning - Fall 2010: Readings in Video Analysis - Fall 2009: Readings in Image Semantics - Fall 2008: Readings in Pattern Theory - Fall 2007: Readings in Medical Image Segmentation

Prior Experience as a Postdoc and Graduate Student Object-Oriented Methods in Software Engineering - UCLA BIOMED 223C, Spring 2006. Research Experience for Undergraduates Mentorship - Luz Molinelli, Summer 2005. Project: Retinal disease diagnosis through multidimensional histogram analysis. Research Experience for Undergraduates Mentorship - Ravi Mody, Summer 2004. Project: Machine learning to track hand postures. Guest Lecturer - Computer Vision, Cameras and Calibration, Dr. Gregory Hager, Fall 2002. Teaching Assistant - Computer Vision, Dr. Gregory Hager, Fall 2001. Duties included holding weekly office hours, grading homeworks and projects, and preparing review notes. Teaching Assistant - Data Structures, Dr. Subodh Kumar in Fall 2000 and Dr. Jonathan Cohen in Spring 2001. Duties included managing a team of 5 course assistants, holding weekly office hours, grading projects and exams, and holding review sessions.

Student Advising Ph.D. Students University of Michigan D12. Eric Hofesmann (CSE) Expected Spring 2023 D11. Byungsu Kyle Min (ECE) Expected Spring 2022 D10. Victoria Florence (ROB) Expected Spring 2022 D9. Stephan Lemmer (ROB) Expected Spring 2022 D8. Nathan Louis (ECE) Expected Spring 2022 D7. Luowei Zhou (ROB) Expected Spring 2020 D6. Madan Ravi Ganesh (ECE) Expected Spring 2020 D5. Shurjo Banerjee (ECE) Expected Spring 2020 D4. Parker Koch (ECE) Expected Spring 2020 D3. Ryan Szeto (CSE ) Expected Spring 2020 D2. Vikas Dhiman (ECE) 6/2019 Thesis: Towards Better Navigation Initial Placement: PostDoc at University of California San Diego D1. Chenliang Xu (CSE) 8/2016 Thesis: Scale-Adaptive Video Understanding Initial Placement: Assistant Professor at University of Rochester CS

SUNY at Buffalo D’10. Liang Zhao Expected Spring 2018 D’9. Duygu Sarikaya 6/2017 Thesis: Exploring Fusion Models in Computer Vision for Medical Imaging Initial Placement: Postdoctoral Fellow at MediCIS D’8. David Johnson 6/2017 Thesis: From Hierarchies to Metrics: Learning Nonlinear Models of Semantics Association Initial Placement: Postdoctoral Fellow at the University of Michigan D’7. Wei Chen 8/2015 Thesis: Video Based Action Understanding Initial Placement: Software Engineer at Amazon D’6. Ran Xu 8/2015 Thesis: Structured Models for Video Understanding Initial Placement: Data Scientist at Banjo D’5. Kevin R. Keane 8/2015 Thesis: Implementing High Dimensional Gaussian Models For Financial Applications Initial Placement: Systems Trading Group, Maple Securities USA, Inc.

22 of 27 D’4. Caiming Xiong 8/2014 Thesis: Learning From and Actively Selecting Pairwise Constraints in Data Science Initial Placement: Postdoc at UCLA Current: Senior Research at Metamind D’3. Jeffrey A. Delmerico 8/2013 Thesis: Attributed Object Maps: Descriptive Object Models as High-level Semantic Features for Mobile Robotics Placement: Postdoc at ETH Zurich D’2. Albert Y. C. Chen 5/2013 Thesis: Modeling and Optimizing Spatiotemporal Priors for Video Analysis Problems Initial Placement: Computer Scientist at Tandent Vision Science (Pittsburgh, PA) Current: CTO Viscovery, Inc. D’1. Ifeoma Nwogu, Ph.D. 8/2009 Jointly advised with Prof. Venu Govindaraju Thesis: An Ontology Driven Probabilistic Methodology for Image Understanding Placement: NSF Computing Innovation Fellowship at U. of Rochester Current: Research Faculty at SUNY at Buffalo

M.S.E. Students SUNY at Buffalo M8. Duygu Sarikaya 6/2012 Thesis: Detection and Segmentation of Free Blood in FAST Exam Ultrasound Images Placement: Ms. Sarikaya is a Ph.D. student at SUNY at Buffalo M7. Ananth Sadanand 2/2012 Thesis: Action Bank: A High-Level Representation of Activity in Video Placement: Mr. Sadanand is a Computer Vision Engineer at Liveclips.com in New York, NY. M6. Sagar Waghmare 2/2012 Thesis: Comparative Study of Feature-Selective Sliding Window Object Detectors in Images Placement: Mr. Waghmare is a Computer Vision Programming Specialist at a startup in New York City. M5. Xin Li, M.S.E. 8/2011 Thesis: Key-Part Detection Using Boundary-Regional Codebook Placement: Mr. Li is a Ph.D. student at Temple University. M4. Yingjie Miao, M.S.E. 6/2011 Project: Hamiltonian Streamline Guided Feature Extraction with Application to Face Detection Placement: Dr. Miao is a Machine Learning Engineer at SAP. M3. Timothy J. Burns, M.S.E. 6/2010 Project: Document Image Segmentation and Labeling with Topic Models Placement: Mr. Burns is a Software Engineer in Buffalo, NY. M2. Dipankar Das, M.S.E. 12/2009 Thesis: Hierarchical Multiple Instance Learning for Object Detection Placement: Mr. Das is a Research Engineer at Ikona Medical in Santa Monica, CA. M1. Chris Hoeflich, M.S.E. 12/2008 Project: Segmentation of 2D Gel Electropheresis Spots Using a Markov Random Field. Placement: Mr. Hoeflich is a Software Engineer in Buffalo, NY.

Undergraduate Students In the capacity that I mentor them in research.

University of Michigan U4. Samuel Tenka 6/2018 U3. Max Morrison 6/2018 U2. Yichen Yao 6/2017 U1. Sajan Patel 6/2016

SUNY at Buffalo U’6. Spencer Whitt 6/2014 U’5. Philip Rosebrough 6/2012 23 of 27 U’4. Steven Hsieh 6/2012 U’3. Colin Lea 6/2011 U’2. Alexander Haynie 6/2011 U’1. Andrew Schlackman 6/2009

Ph.D. and M.S.E. Committee Membership Students for whom I am not the primary advisor. University of Michigan Z13. Xinchen Yan, Ph.D. Candidate (CSE) Advisor: Prof. Honglak Lee Z12. Arash Ushani, Ph.D. Candidate (CSE) Advisor: Prof. Ryan Eustice Z11. Alexander Kalinin, Ph.D. Candidate (Bioinformatics) Advisors: Prof. Brian Athey and Prof. Ivo Dinov Z10. Yu-Wei Chao, Ph.D. Candidate (CSE) Advisors: Prof. Jia Deng Z9. John Lipor, Ph.D. (EE:Systems) Granted Fall 2017 Advisors: Prof. Laura Balzano Sensing Structured Signals with Active and Ensemble Methods Z8. Jie Li, Ph.D. (EE:Systems) Granted Summer 2017 Advisors: Prof. Matthew Johnson-Roberson and Prof. Ryan Eustice Place Recognition and Localization for Multi-Modal Underwater Navigation with Vision and Acous- tic Sensors Z7. Matthew Jacobs, Ph.D. (Math) Granted Spring 2017 Advisors: Prof. Selim Esedoglu¯ and Jinho Baik Algorithms for Multiphase Partitioning Z6. Suyog Jain, Ph.D (UT Austin) Granted Spring 2017 Advisor: Prof. Kristen Grauman (UT Austin) Human Machine Collaboration for Foreground Segmentation in Images and Videos Z5. Guillaume Seguin, Ph.D. (INRIA Paris) Granted Spring 2016 Advisor: Prof. Ivan Laptev (INRIA Paris) Analyse des personnes dans les films st´er´escopiques Z4. Yelin Kim, Ph.D (CSE) Granted Spring 2016 Advisor: Prof. Emily Mowers Provost Automatic Emotion Recognition: Quantifying Dynamics and Structure in Human Behavior Z3. Dan Oneata, Ph.D. (INRIA Grenoble) Granted Summer 2015 Advisor: Prof. Cordelia Schmid (INRIA Grenoble, U. Grenoble) Mod`elesrobustes et efficaces pour la reconnaissance d’actions et leur localisation (Robust and efficient models for action recognition and localization) Z2. Yu Xiang, Ph.D. (EE:Systems) Granted Winter 2015 Advisors: Prof. Silvio Savarese and Prof. Alfred Hero 3D Object Representations for Recognition Z1. Paul Ozog, Ph.D. (EE:Systems) Granted Winter 2015 Advisor: Prof. Ryan Eustice Advances in Simultaneous Localization and Mapping in Confined Underwater Environments Using Sonar and Optical Imaging

SUNY at Buffalo Z’12. Jingteng Xue, Ph.D. Granted Spring 2014 Advisor: Prof. Chang Wen Chen Perceptual Quality Driven Video Evaluation and Processing Z’11. Wenyuan Yin, Ph.D. Granted Summer 2013 Advisor: Prof. Chang Wen Chen Mobile Multimedia: From Acquisition to Adaptation with Semantics, Context and Social Information Z’10. Shujie Liu, Ph.D. Granted Spring 2013 Advisor: Prof. Chang Wen Chen Compression, Rendering and Transmission for 3D and Scalable Video

24 of 27 Z’9. Yi Tang, Ph.D. Granted Summer 2012 Advisor: Prof. Sargur Srihari Evaluating the Probability of Identification in Forensic Science Z’8. Chang Su, Ph.D. Granted Summer 2011 Advisor: Prof. Sargur Srihari Machine Learning in Fingerprint Probability Evaluation Z’7. Ricardo Rodrigues, Ph.D. Granted Summer 2011 Advisor: Prof. Venu Govindaraju Face Modeling and Biometric Anti-Spooking using Probability Distribution Transfer Learning Z’6. Anh Ngoc Le, Ph.D. Granted Spring 2011 Advisor: Prof. Hung Ngo. On the Data Flow Masquerading Problem Z’5. Xujun Peng, Ph.D. Granted Fall 2010 Advisor: Prof. Venu Govindaraju. Probabilistic Random Field Based Text Identification From Annotated Machine Printed Documents Z’4. Gabriel Terajanu, Ph.D. Granted Spring 2010 Advisor: Prof. Peter Scott Towards a Decision-Centric Framework for Uncertainty Propagation and Data Assimilation Z’3. Bhaskar Purkayastha, M.S.E. Granted Fall 2009 Advisor: Prof. Venu Govindaraju Integrating Gesture Recognition and Speech Recognition in a Touch-Less Human Computer Interac- tion System. Z’2. Peter Noel,¨ Ph.D. Granted Summer 2009 Advisor: Prof. Jinhui Xu Geometric Algorithms for Three Dimensional Reconstruction in Medical Imaging Z’1. Hani Z. Girgis, Ph.D. Granted Summer 2008 Advisor: Prof. Daniel Fischer Machine Learning Based Meta Approaches to Protein Structure Prediction

Visiting Scholars V8. Haonan Chen (Tsinghua University, China; Undergrad) 6/2016–9/2016 V7. Jiamei Yan (Zhejian University, China; Undergrad) 6/2016–9/2016 V6. Baiyun Cui (Zhejian University, China; Undergrad) 6/2016–9/2016 V5. Tingtin Han (Harbin Institute of Technology, China) 9/2015-8/2016 V4. David Molik (Rensselaer Polytechnic Institute, Undergrad) Summer 2012 V3. Wei Wu (Assoc. Professor, School of Information Engineering, Wuhan University of Tech- nology) 2/2011-2/2012 V2. Srijan Kumar (IIT Kharagpur, Undergrad) Summer 2011 V1. Digvijay Gagneja (IIT Kharagpur, Undergrad) Summer 2010

Industrial CEO and Co-Founder for Voxel51, Inc Ann Arbor, MI 12/2016–Current Activities Board of Advisors for Reflective.AI San Francisco, CA 6,2019–Current Board of Advisors for Onu Technology, Inc. San Francisco, CA 1,2017–Current Consultant for SoarTech, Inc. Ann Arbor, MI 3/2016–Current Consultant for Toyota Research Institute, Inc. Ann Arbor, MI 5/2016–4/2017 Consultant for Cyvek, Inc. Wallingford, CT 4/2015–4/2016 Consultant for NEC Research, Inc. Cupertino, CA 8/2014–6/2015 Consultant for CapsoVision, Inc. Santa Clara, CA 8/2014–Current Consultant for CUBRC, Inc. Buffalo, NY 12/2009–3/2014 Various projects related to computer vision and image analysis for defense contracts. Consultant for Ikona Medical Corp. Los Angeles, CA 9/2006–6/2014 Development of real-time medical video mosaicking algorithms and software.

25 of 27 Licensed Technology 9/2009 Licensed GPU based reconstruction algorithm for CT data to IRIS (Ionizing Radiation Imaging Systems LLC). Co-Founder of NaviGuru.com Live 4/2006–11/2009 NaviGuru.com was a Web 2.0 site that unifies social networking with on-line mapping technology. It introduced a new form of web search called visual query. Consultant for Infinite Biomedical Technologies, LLC Baltimore, MD 9/2006–9/2008 Development of image calibration and dewarping algorithm used in contact endoscopy. Provisional Patent with Licensable Technology 2003 Title: 4D Touchpad - VICs based interface to computer systems. Institute: Johns Hopkins University, Baltimore MD (JHU Ref. DM-4181). Co-Inventors: Gregory D. Hager and Darius Burschka. Description: The 4D Touchpad builds a shared perceptual space between the computer user and a set of video cameras. Perceptual gestures are used to directly interact with interface components. The video cameras sense and interpret the gestures and effect automation in the computer system.

Full Education University of California, Los Angeles Los Angeles, CA Post-Doc in Neuroscience and Statistics 2006-2007 Advisors: Dr. Alan Yuille and Dr. Arthur Toga

The Johns Hopkins University Baltimore, MD Ph.D. in Computer Science 6/2006 Advisor: Dr. Gregory D. Hager Dissertation Title:“Techniques for Vision-Based Human-Computer Interaction”

The Johns Hopkins University Baltimore, MD M.S.E. in Computer Science 6/2002 Project 1 Advisor: Dr. Gregory D. Hager, Computational Interaction and Robotics Lab (CIRL) Project 1 Title:“Planar Surface Tracking Using Direct Stereo” Project 2 Advisor: Dr. Jonathan Cohen, Graphics Lab Project 2 Title:“Out-Of-Core Voxelization of Large Scalar Fields for Interactive Multiresolution Volume Rendering”

Loyola College in Maryland Baltimore, MD B.S. in Computer Science, Cum Laude, Ranked First in Major 5/2000 Advisor: Dr. Roger Eastman

Chaminade High School Mineola, NY

Past Positions Associate Professor (with tenure) Ann Arbor, MI Electrical Engineering and Computer Science University of Michigan 8/2014 - 8/2019 Associate Professor (with tenure) Buffalo, NY Computer Science and Engineering State University of New York at Buffalo 8/2013 - 8/2014 Assistant Professor Buffalo, NY Computer Science and Engineering State University of New York at Buffalo 8/2007-8/2013 Post-Doctoral Fellow Los Angeles, CA Neuroscience and Statistics University of California, Los Angeles 9/2006-11/2007 Mentors: Drs. Alan Yuille and Arthur Toga Primary Focus: Develop automatic, efficient and robust segmentation and recognition techniques for computational neuroimaging problems with coupled statistical learning methods. Implement and deploy software tools based on these algorithms into the research community. Post-Doctoral Fellow Los Angeles, CA Radiological Sciences and Statistics University of California, Los Angeles 9/2005-8/2006 Mentors: Drs. Alan Yuille and Ricky Taira Primary Focus: Develop automatic segmentation and recognition techniques for medical imaging

26 of 27 problems (e.g., brain tumor) by integrating bottom-up detection with top-down models. Quantify statistics of the models’ shape and appearance to improve accuracy of diagnosis and treatment. Research Assistant Baltimore, MD Computer Science The Johns Hopkins University 8/2001-8/2005 Advisor: Dr. Gregory D. Hager Project: Developing vision-based techniques enabling dynamic, complex interaction in immer- sive mixed-reality environments: the VICs project. Research Intern Princeton, NJ Siemens Corporate Research Summer 2003 Mentor: Dr. Yakup Genc Project: Markerless, real-time camera pose tracking using stereo video for Augmented Reality. Software Engineer Baltimore, MD The Johns Hopkins University Fall 2001 Description: Contracted by the Department of Computer Science at The Johns Hopkins Uni- versity to design and development a SQL-based database and WWW interface for the faculty recruitment/search process. The system remains in use today with no downtime. Acting Director Of Technology Baltimore, MD Bionic Box Inc. 5/2000-9/2000 Description: Responsible for all internal IT and managed all (participated in some) software development projects. Software Engineer Baltimore, MD Alexander and Tom, Inc. 9/1999-5/2000 URL: http://www.alextom.com Responsibilities: Design and development of a broad range of interactive systems including small video-games, database systems, websites, and custom interactive cd-roms. Research Intern Rockville, MD Earth Satellite Corporation 6/1999-12/2000 URL: http://www.earthsat.com Project: Modify and deploy NASA software for radiometrical and geometrical distortion correc- tion for the Landsat 7 satellite. Research Assistant Baltimore, MD Computer Science Loyola College in Maryland Spring 1999 Advisor: Dr. Keith Gallagher Project: Development of an ISO 9000-3 compatible software project management tool. Hauber Science Research Fellow Baltimore, MD Computer Science Loyola College in Maryland Summer 1998 Advisor: Dr. Roger Eastman Project: Development of an image-processing algorithm for robust registration of retinal nerve images for use in glaucoma diagnosis. Database Programmer Manhattan, NY Information Builders, Inc. Summer 1996, 1997 and Winter 1997 URL: http://www.informationbuilders.com Responsibilities: Fulfill internal database programming needs for information systems using their proprietary database language and development platforms (FOCUS).

27 of 27